RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917000931966976 |
|---|---|
| author | Ye-Bin, Moon Miles, Roy Oh, Tae-Hyun Elezi, Ismail Deng, Jiankang |
| author_facet | Ye-Bin, Moon Miles, Roy Oh, Tae-Hyun Elezi, Ismail Deng, Jiankang |
| contents | Image retouching not only enhances visual quality but also serves as a means of expressing personal preferences and emotions. However, existing learning-based approaches require large-scale paired data and operate as black boxes, making the retouching process opaque and limiting their adaptability to handle diverse, user- or image-specific adjustments. In this work, we propose RetouchLLM, a training-free white-box image retouching system, which requires no training data and performs interpretable, code-based retouching directly on high-resolution images. Our framework progressively enhances the image in a manner similar to how humans perform multi-step retouching, allowing exploration of diverse adjustment paths. It comprises of two main modules: a visual critic that identifies differences between the input and reference images, and a code generator that produces executable codes. Experiments demonstrate that our approach generalizes well across diverse retouching styles, while natural language-based user interaction enables interpretable and controllable adjustments tailored to user intent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08054 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models Ye-Bin, Moon Miles, Roy Oh, Tae-Hyun Elezi, Ismail Deng, Jiankang Computer Vision and Pattern Recognition Image retouching not only enhances visual quality but also serves as a means of expressing personal preferences and emotions. However, existing learning-based approaches require large-scale paired data and operate as black boxes, making the retouching process opaque and limiting their adaptability to handle diverse, user- or image-specific adjustments. In this work, we propose RetouchLLM, a training-free white-box image retouching system, which requires no training data and performs interpretable, code-based retouching directly on high-resolution images. Our framework progressively enhances the image in a manner similar to how humans perform multi-step retouching, allowing exploration of diverse adjustment paths. It comprises of two main modules: a visual critic that identifies differences between the input and reference images, and a code generator that produces executable codes. Experiments demonstrate that our approach generalizes well across diverse retouching styles, while natural language-based user interaction enables interpretable and controllable adjustments tailored to user intent. |
| title | RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.08054 |